How MCP Python SDK scored an A.

• code

  79/100
  • ✓ Contributors & bus-factor: 7 recent contributors — concentrated
  • ✓ Commit recency: last commit 5d ago
  • ✓ Commit cadence: 116 commits in 90 days
  • ✓ Issue close ratio: 81% of issues closed
  • ✓ Release cadence: 33 releases in 12 months
  • ✓ Stars (log-damped): 24,641 stars (log-damped)
  • – Star authenticity: star-velocity check unavailable — GitHub no longer publishes stargazer timestamps for this repo
  • – Dependent repos: not measurable — no package listing on a registry we can query

• identity

  80/100
  • ✓ Organisation: Built by Model Context Protocol · notable organization (verified: Org profile shows a Verified badge for modelcontextprotocol.io; profile website https://modelcontextprotocol.io, description "An open protocol that enables seamless integration between LLM applications and external data sources and tools.".)

• audits

  Not measured
  • – Third-party scans: not measurable — no registry listings for this tool

• freshness

  100/100
  • ✓ Last shipped: last commit 5d ago — fast-churn frameworks are expected to ship about every 60d

• community

  23/100
  • – Recommends: no recommends from gate-passing builders yet
  • ✓ Hacker News mentions: 1 Hacker News story pointing at this tool
  • – Signal depth: sparse data — this is an early reading from very few data points

Identity and Community did not lower this score. Identity and Community can only ever add. They did not raise the average for MCP Python SDK, so the score shown is the one it would have without them. The components are still listed above, with their real values.

Components that could not be measured are left out of the average entirely, and their weight is redistributed, never scored as zero. Identity and Community are left out the same way when they would not have raised the score. How scores are calculated.